Review

[논문리뷰] Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

Hong Jiao이 arXiv에 게시한 'Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Item Difficulty Prediction #Human-AI Alignment #Proficiency Simulation #Metacognition #Curse of Knowledge #Educational Assessment #Zero-shot Learning

2025년 12월 22일

[논문리뷰] Brain-Grounded Axes for Reading and Steering LLM States

Sandro Andric이 arXiv에 게시한 'Brain-Grounded Axes for Reading and Steering LLM States' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Interpretability #Brain-Grounded AI #MEG #Phase-Locking Value #ICA #LLM Steering #Neural Decoding #Latent Space

2025년 12월 22일

[논문리뷰] When Reasoning Meets Its Laws

Liu Ziyin이 arXiv에 게시한 'When Reasoning Meets Its Laws' 논문에 대한 자세한 리뷰입니다.

#Review #Large Reasoning Models #Reasoning Behaviors #Compute Law #Accuracy Law #Monotonicity #Compositionality #Fine-tuning #LORE-BENCH

2025년 12월 21일

[논문리뷰] Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

Lihong Li이 arXiv에 게시한 'Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Turn Reinforcement Learning #LLM Agents #Proximal Policy Optimization (PPO)#Turn-Level MDP #Advantage Estimation #Generative AI #Deep Reinforcement Learning

2025년 12월 21일

[논문리뷰] StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models

arXiv에 게시된 'StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Autoregressive Models #Image Generation #Model Acceleration #Low-Rank Approximation #Semantic Irrelevance #Stage-Aware Optimization #Text-to-Image Synthesis

2025년 12월 21일

[논문리뷰] Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

arXiv에 게시된 'Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience' 논문에 대한 자세한 리뷰입니다.

#Review #Formal Theorem Proving #Large Language Models #Reinforcement Learning #Agentic Prover #Lean Theorem Prover #Mathematical Reasoning #Test-Time Scaling

2025년 12월 21일

[논문리뷰] SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories

arXiv에 게시된 'SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories' 논문에 대한 자세한 리뷰입니다.

#Review #Software Engineering Benchmarks #Large Language Models (LLMs)#Code Generation #Automated Benchmark Generation #Multilingual #GitHub Pull Requests #Test Oracle #Fine-tuning

2025년 12월 21일

[논문리뷰] Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Runtao Liu이 arXiv에 게시한 'Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models (MLLMs)#Visual Degradation #Robustness #Reasoning Chains #Supervised Fine-Tuning (SFT)#Reinforcement Learning (RL)#Degradation-Aware Reasoning #Interpretability

2025년 12월 21일

[논문리뷰] RadarGen: Automotive Radar Point Cloud Generation from Cameras

Or Litany이 arXiv에 게시한 'RadarGen: Automotive Radar Point Cloud Generation from Cameras' 논문에 대한 자세한 리뷰입니다.

#Review #Radar Point Cloud Generation #Diffusion Models #Camera-to-Radar #BEV Representation #Autonomous Driving #Multi-modal Generative Models #Scene Editing

2025년 12월 21일

[논문리뷰] Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Yuhao Zhou이 arXiv에 게시한 'Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows' 논문에 대한 자세한 리뷰입니다.

#Review #Scientific General Intelligence (SGI)#LLMs #Benchmarking #Scientist-Aligned Workflows #Practical Inquiry Model #Multi-modal Reasoning #Code Generation #Test-Time Reinforcement Learning (TTRL)

2025년 12월 21일

[논문리뷰] Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

arXiv에 게시된 'Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers' 논문에 대한 자세한 리뷰입니다.

#Review #Language Models #Transformer Architecture #Canon Layers #Synthetic Pretraining #Reasoning Depth #Linear Attention #State-Space Models #NoPE

2025년 12월 21일

[논문리뷰] PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

arXiv에 게시된 'PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #Egocentric Data #Physical Intelligence #VLM #Robot Control #Embodied AI #VQA Supervision #Human-Robot Interaction #Zero-shot Transfer

2025년 12월 21일

[논문리뷰] Meta-RL Induces Exploration in Language Agents

Maria Brbic이 arXiv에 게시한 'Meta-RL Induces Exploration in Language Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Meta-RL #LLM Agents #Exploration #Reinforcement Learning #Policy Adaptation #In-context Learning #Self-reflection #Multi-episode tasks

2025년 12월 21일

[논문리뷰] HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering

arXiv에 게시된 'HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering' 논문에 대한 자세한 리뷰입니다.

#Review #Video Question Answering #Multi-evidence Integration #Video-LLMs #Benchmark #Temporal Reasoning #Frame Selection #Evidential Requirement #MRFS

2025년 12월 21일

[논문리뷰] GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

arXiv에 게시된 'GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Grounding #MLLMs #Benchmark #Multi-Dimensional Evaluation #Rejection Capability #Test-Time Scaling #Data Mixture Training

2025년 12월 21일

[논문리뷰] Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

arXiv에 게시된 'Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing' 논문에 대한 자세한 리뷰입니다.

#Review #Text-to-Image Generation #Image Editing #Representation Encoders #Latent Diffusion Models #Variational Autoencoder (VAE)#Semantic Reconstruction #Off-manifold Latents #DINOv2

2025년 12월 21일

[논문리뷰] Are We on the Right Way to Assessing LLM-as-a-Judge?

arXiv에 게시된 'Are We on the Right Way to Assessing LLM-as-a-Judge?' 논문에 대한 자세한 리뷰입니다.

#Review #LLM-as-a-Judge #Evaluation Metrics #Consistency #Robustness #Positional Bias #Transitivity #Situational Preference #Multi-agent Systems

2025년 12월 21일

[논문리뷰] An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges

arXiv에 게시된 'An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Embodied Intelligence #Robotics #Foundation Models #Multi-modal Learning #Reinforcement Learning #Sim-to-Real Transfer #Human-Robot Interaction

2025년 12월 21일

[논문리뷰] 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

arXiv에 게시된 '4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #4D Understanding #Perceptual Distillation #Region-level VQA #Video Question Answering #Temporal Perception #Depth Perception

2025년 12월 21일

[논문리뷰] 3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework

Hendrik P. A. Lensch이 arXiv에 게시한 '3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework' 논문에 대한 자세한 리뷰입니다.

#Review #3D Reconstruction #Generative AI #Indoor Scenes #Compositional Framework #Differentiable Rendering #Image-to-3D #VFX #Game Development

2025년 12월 21일